TRI-AD completes successful creation of HD maps for automated driving
Posted: 11 March 2020 | Sam Mehmet (Intelligent Transport)
The proof of concepts demonstrated by Toyota’s automated driving software development company, TRI-AD, are said to expand map coverage and reduce the time needed for map updates.
Toyota Research Institute-Advanced Development, Inc. (TRI-AD) has completed proof of concepts (PoC) demonstrating high definition (HD) map building for surface roads with relative accuracy of less than 50 centimetres – considered a good level that is required for automated driving.
In these PoCs, TRI-AD verified that both following methods are effective for HD map building:
- Building map information for automated driving via map data derived from the cameras of ordinary vehicles as well as satellite imagery, without the use of conventional means of collecting data such as survey vehicles
- Applying vehicle data from TRI-AD’s Automated Mapping Platform (AMP) to other companies’ platforms by converting data formats and applying correcting algorithms.
By utilising the results of these PoCs, it is expected that the delay in updating HD maps for automated driving can be shortened, areas of HD map coverage can reportedly be expanded quickly, and costs to build and maintain the HD maps can be reduced.
Maxar Technologies (Maxar)
Maxar Technologies (Maxar), a partner and innovator in Earth Intelligence and Space Infrastructure, Japan’s IT services provider NTT DATA Corporation (NTT DATA), and TRI-AD are collaborating on a proof of concept to build automated HD maps for automated vehicles using the highest-resolution commercial satellite imagery since April 2019.
The PoC reportedly demonstrated that it is now possible to automatically extract the required map information by analysing and removing and correcting non-map image pixels such as automobiles, shadows, and occlusions due to the inclination of buildings in satellite imagery. Currently, maps with a relative accuracy of 25 centimetres1 were created within the 23 wards in Tokyo, as well as six cities globally, and were verified to be useful for automated driving purposes.
TRI-AD and a road intelligence platform, CARMERA Inc. (CARMERA), have also successfully conducted a camera-based HD mapping initiative. As part of their global partnership, the collaboration used “dashcam” drive recorders to detect and place key road features – such as lane markings, traffic signals and signs- within the 23 wards in Tokyo and two cities in the U.S..
The project achieved a relative accuracy of 40 centimetres1 for key navigation feature – -a major advance in camera-only detection. TRI-AD’s work with CARMERA used the same hardware-agnostic computer vision and processing technology as CARMERA’s Real-Time Events and Change Management engine, which detects, validates and delivers navigation-critical updates to CARMERA’s regenerative HD mapping system in minutes rather than months. By using consumer-grade vehicle cameras that are common around the world, TRI-AD and CARMERA are said to have showcased a scalable approach to next-generation map making.
TRI-AD also collaborated on a PoC with TomTom International BV. (TomTom), an independent location technology specialist. Together, the companies showed that lower-class roads (urban roads), including lane markings necessary for automated driving, could be successfully created or updated in near real-time on TomTom’s HD map. The solution was achieved by verifying the reliability of the vehicle data collected by TRI-AD’s AMP, and then converting it for input into TomTom’s cloud-based transactional mapmaking platform.
TRI-AD also collaborated with location data and technology platform, HERE Technologies (HERE) for this PoC. Correcting the positional errors in the vehicle data collected by TRI-AD, HERE was able to automatically create surface road maps using HERE’s advanced ‘Self-Healing’ technology. By using only vehicle sensor data, HERE ingested the data into its platform and automatically generated HD maps including lane level information required for automated driving.
Mandali Khalesi, Vice President of Automated Driving Strategy and Mapping at TRI-AD, said, “I’m very pleased to announce the results of the PoCs with Maxar and NTT DATA, and CARMERA, and also the results of our new demonstration partners, TomTom and HERE. We got a step closer to a future where automated driving becomes a safer and more accessible technology for all. We will continue to cooperate with partners as we further refine our accuracy.”
1. Reference values in some environments with good data accuracy in the target areas of these PoCs.